BF lz-skill-vetter-plus
OpenClaw 技能自动化审计器 Pro（安全/性能/质量三维度 38 条规则）。基于 spclaudehome v1.0.0 fork 深度升级，新增 JSON 报告、CI 退出码、豁免机制、severity-cap 引擎适配。安装第三方技能前必跑。触发词：vet skill, audit skill, 安全审计, 扫描 skill, skill 检查.
OpenClaw 技能自动化审计器 Pro（安全/性能/质量三维度 38 条规则）。基于 spclaudehome v1.0.0 fork 深度升级，新增 JSON 报告、CI 退出码、豁免机制、severity-cap 引擎适配。安装第三方技能前必跑。触发词：vet skill, audit skill…
As a process F 31/100 · Will not run — References files that are not bundled: references/_*.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 11
✓ No critical or high findings
Medium and low: 11
-
low Dangerous commands
cmd-privilegereferences/_rules_documentation.md:52Privilege escalation / world-writable permissions (documentation of a security skill)- SEC-SYS-002 chmod 777
security skill -
low Dangerous commands
cmd-privilegereferences/patterns.md:62Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)| SEC-SYS-001 | `sudo` / `setuid` | 🟠 high |
tablesecurity skill -
low Dangerous commands
cmd-privilegereferences/patterns.md:64Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)| SEC-SYS-003 | `chmod 777` 全开 | 🟡 medium |
tablesecurity skill -
low Dangerous commands
cmd-privilegereferences/patterns.md:123Privilege escalation / world-writable permissions (documentation of a security skill)os.setuid(0) # safe-pattern: doc-example，非真实调用
security skill -
low Dangerous commands
cmd-privilegescripts/patterns/red_flags.yml:177Privilege escalation / world-writable permissions (string literal in code, not executed)name: "sudo / setuid"
code literal -
low Dangerous commands
cmd-privilegescripts/patterns/red_flags.yml:179Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)regex: '\b(sudo\s|chmod\s+[0-7]*[4-7][0-7]*|setuid|setgid)\b'
detectorcode literal -
low Dangerous commands
cmd-privilegescripts/patterns/red_flags.yml:191Privilege escalation / world-writable permissions (string literal in code, not executed)name: "chmod 777 全开"
code literal -
low Dangerous commands
cmd-privilegeSKILL.md:99Privilege escalation / world-writable permissions (documentation of a security skill)os.setuid(0)
security skill
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/_*.md
Process rating: all ten parameters 31/100
- 0Tools and files. 1 referenced file(s) missing: references/_*.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (lz-skill-vetter-plus) differs from the folder (lz-skill-vetter-20260819)
- 100Steps. 45 steps
- 100Execution cost. Instruction body is 1473 tokens
- 100Running it twice. No mutating operations
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -253 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 180: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.